CN113688773A - Storage tank dome displacement data restoration method and device based on deep learning - Google Patents
Storage tank dome displacement data restoration method and device based on deep learning Download PDFInfo
- Publication number
- CN113688773A CN113688773A CN202111030325.0A CN202111030325A CN113688773A CN 113688773 A CN113688773 A CN 113688773A CN 202111030325 A CN202111030325 A CN 202111030325A CN 113688773 A CN113688773 A CN 113688773A
- Authority
- CN
- China
- Prior art keywords
- displacement data
- data
- 1dcnn
- measuring point
- storage tank
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to a storage tank dome displacement data restoration method based on deep learning, belonging to the technical field of displacement data restoration, and the restoration method comprises the following steps: obtaining historical displacement data of the measuring points to be repaired and the surrounding associated measuring points, decomposing the historical displacement data into a plurality of intrinsic mode function components through a set empirical mode decomposition algorithm, training the 1DCNN-BiLSTM model to obtain an EEMD-1DCNN-BiLSTM model, predicting missing displacement data through the EEMD-1DCNN-BiLSTM model, and completing data repair. According to the method, the EEMD, the 1DCNN and the BilSTM are combined into a new model, the method is very suitable for processing complex long-term time sequence dynamic information with spatial correlation, can greatly improve the prediction precision, and is very suitable for repairing the missing displacement data of the LNG storage tank dome.
Description
Technical Field
The invention belongs to the technical field of storage tank dome displacement data restoration, and relates to a storage tank dome displacement data restoration method and device based on deep learning.
Background
The adoption of the displacement sensor has great significance for evaluating the dynamic response of the LNG storage tank structure. However, in the shaking table experiment, some displacement sensors may fail or be abnormal, so that data is lost, and the data is difficult to recover.
The existing method for predicting the structural displacement of the LNG storage tank based on an artificial intelligence method is mainly divided into two methods. One method is a 'shallow layer' machine learning method, acceleration sensing data has high nonlinearity and non-Gaussian, and a 'shallow layer' model has certain limitation on long-term prediction of displacement response, cannot process massive monitoring data and has low accuracy. The other method is a traditional deep neural network model and has the characteristics of universality, high efficiency and the like, but the accuracy needs to be further improved. Therefore, the existing prediction methods cannot be used to repair the displacement data of the sensor.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for repairing displacement data of a storage tank dome based on deep learning of an EEMD-1DCNN-BilSTM model.
In order to achieve the purpose, the invention provides the following technical scheme:
a storage tank dome displacement data restoration method based on deep learning is used for restoration when LNG storage tank dome displacement data are missing, and comprises the following steps:
step S1, taking a measuring point with LNG storage tank dome displacement data missing as a measuring point to be repaired, selecting a plurality of measuring points around the measuring point to be repaired as associated measuring points, acquiring historical displacement data of the measuring point to be repaired in a certain period before the data missing period and historical displacement data of the associated measuring points in a corresponding period, and decomposing the historical displacement data of the measuring points into a plurality of intrinsic mode function components respectively through a set empirical mode decomposition algorithm;
step S2, taking the intrinsic mode function component obtained through decomposition as an input feature of a 1DCNN-BilSTM model, extracting a spatial correlation feature of the displacement of the associated measuring point and the displacement of the measuring point to be repaired through the 1DCNN model, and then sending the extracted spatial correlation feature into the BilSTM model to obtain a dependency characteristic in time;
step S3, defining a loss function of the 1DCNN-BilSTM model, and ending training when the value of the loss function of the 1DCNN-BilSTM model converges to a fixed value and keeps unchanged to obtain an EEMD-1DCNN-BilSTM model;
step S4, obtaining displacement data of the measuring point to be repaired before the data missing period and displacement data of the associated measuring point before the data missing period and the data missing period, inputting the displacement data into an EEMD-1DCNN-BilSTM model to predict the displacement data of the measuring point to be repaired at the data missing period; and taking the predicted displacement data as displacement data of the measuring point to be repaired in the data missing period to finish the repair of the missing data.
Further, the ensemble empirical mode decomposition algorithm is implemented by the following steps:
step S11, selecting the processing times m of the original signal;
s12, selecting m random white noises with different amplitudes, and combining the original signal with each white noise respectively to obtain m new signals;
step S13, performing empirical mode decomposition on the m new signals respectively to obtain a series of intrinsic mode function components;
and step S14, respectively averaging the intrinsic mode function components of the corresponding modes to obtain a set empirical mode decomposition result.
Further, the scales of m white noises are uniformly distributed, and the energy of the white noises is also uniformly distributed on the frequency spectrum.
Further, the empirical mode decomposition algorithm is realized by the following steps:
s131, taking a new signal obtained by combining the original signal and white noise as a signal x (t) to be decomposed, wherein t represents time;
s132, screening a signal x (t) to be decomposed; the method specifically comprises the following steps: finding all the signals x (t) to be decomposedFitting the maximum value point into an upper envelope line of the signal to be decomposed; finding out all minimum value points of the signal x (t) to be decomposed, and fitting the minimum value points into a lower envelope curve of the signal to be decomposed; calculating the mean value of the upper envelope and the lower envelope to obtain the mean envelope m of the signal x (t) to be decomposed1(t); subtracting m from the signal x (t) to be decomposed1(t) obtaining an intermediate component function d1,1(t)；
Step S133, judgment d1,1(t) whether the condition for the eigenmode function component is satisfied, and if not, d1,1(t) instead of the signal to be decomposed x (t), d continues in step S121,1(t) screening, and marking the signal after K times of screening as d1,k(t) up to d1,k(t) when the condition of the eigenmode function component is satisfied, the first IMF component IMF1(t) of the signal x (t) to be decomposed is marked;
step S134, subtracting the first IMF component IMF1(t) from the signal x (t) to be decomposed to obtain a residual component r1(t) to r1(t) continuing the decomposition in steps S12 and S13; after n decompositions, the residual signal r is obtainedn(t); when r isn(t) when the function is a monotonic function, the decomposition is stopped and the residual component function r is usedn(t) as a residual amount RES.
Further, the eigenmode function component satisfies the following condition:
in the whole time range of the function, the number of the extreme points is equal to or different from the number of the zero crossing points by 1;
at any time point, the mean of the upper envelope and the lower envelope is 0.
Further, the time sequence of the displacement data of one measuring point forms one-dimensional data; decomposing the one-dimensional data into a plurality of IMF sequences through EEMD to form two-dimensional data; and after data of a plurality of associated measuring points are obtained, three-dimensional data are formed and are used as an input feature mapping group of the 1DCNN model.
Further, the loss function l (x, y) of the 1DCNN-BilSTM model is defined as:
where N represents the number of samples, xiDenotes the actual value of the i-th sample, yiRepresenting the predicted value of the ith sample.
A deep learning-based storage tank dome displacement data restoration device, comprising:
the displacement data acquisition module is used for acquiring displacement data of each measuring point of the dome of the LNG storage tank in real time and transmitting the displacement data to the calculation analysis module;
the calculation analysis module is used for monitoring whether displacement data of each measuring point of a dome of the LNG storage tank are missing or not in real time, when the displacement data of one measuring point is monitored to be missing, the measuring point with the missing displacement data is used as a measuring point to be repaired, a plurality of measuring points are selected around the measuring point to be repaired to be used as associated measuring points, the displacement data of the measuring point to be repaired and the displacement data of the associated measuring points are input into an EEMD-1DCNN-BilSTM model, the missing displacement data are predicted, the missing displacement data are supplemented by the predicted displacement data, and data repair is completed; and
and the output module is used for outputting the displacement data of each measuring point acquired by the displacement data acquisition module and the repaired displacement data of the measuring point to be repaired.
Further, the calculation analysis module comprises a data reading unit, a monitoring unit, an EEMD-1DCNN-BilSTM model and a storage unit;
the data reading unit is used for reading displacement data of each measuring point of the LNG storage tank dome, which is acquired by the displacement data acquisition module;
the monitoring unit is used for monitoring whether displacement data of each measuring point of the dome of the LNG storage tank is lost or not in real time;
the EEMD-1DCNN-BilSTM model comprises a set empirical mode decomposition unit and a 1DCNN-BilSTM model, wherein the set empirical mode decomposition unit is used for decomposing displacement data of the measuring points to be repaired and each associated measuring point into a plurality of intrinsic mode function components through a set empirical mode decomposition algorithm, and vectors formed by the intrinsic mode function components are used as input characteristics of the 1DCNN-BilSTM model; the 1DCNN-BilSTM model is used for predicting displacement data of missing measuring points to be repaired according to input characteristics;
the storage unit is used for storing displacement data of each measuring point of the LNG storage tank dome acquired by the displacement data acquisition module and displacement data predicted by the EEMD-1DCNN-BilSTM model.
The device further comprises a detection unit and an alarm unit, wherein the detection unit is used for designating a measuring point with normal displacement data as a measuring point to be repaired, comparing the displacement data of the measuring point predicted by the EEMD-1DCNN-BilSTM model with the real displacement data of the measuring point collected by the displacement data collection module, and when the difference value between the displacement data and the measuring point exceeds a preset threshold value, enabling the alarm unit to output an alarm signal to prompt that the predicted data has overlarge offset.
In the invention, EEMD, 1DCNN and BilSTM are combined into a new model, wherein EEMD can decompose complex nonlinear displacement data into linear combinations of eigenmode functions with limited frequencies from high to low, and each decomposed IMF component comprises local characteristic signals of original signals with different time scales; the 1DCNN model has the characteristics of local connection, weight sharing and the like, and can reserve and extract the spatial correlation characteristics among IMFs; the BilSTM model can fully mine the nonlinear relation between variables, adaptively sense the characteristic information of the upper and lower time series, and store the past and future information at any time point, thereby having the capability of capturing the characteristics of the information before and after the acquisition and being very suitable for processing complex problems. Therefore, the combined new model is very suitable for processing complex long-term time sequence dynamic information with space correlation, can greatly improve the prediction precision, and is very suitable for repairing the missing displacement data of the dome of the LNG storage tank. In addition, the EEMD algorithm and the 1DCNN-BilSTM model have low requirements on hardware and low implementation cost.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a flow chart of a preferred embodiment of a deep learning-based storage tank dome displacement data remediation method of the present invention;
FIG. 2 is a schematic diagram of obtaining data of a measuring point to be repaired and a related measuring point for prediction;
FIG. 3 is a schematic diagram of a decomposition of data by the EEMD algorithm;
FIG. 4 is a schematic diagram of the structure of the 1DCNN-BilSTM model;
FIG. 5 is a schematic diagram of a one-dimensional convolutional neural network computation process;
FIG. 6 is a schematic diagram of the architecture of a single neuron architecture of the LSTM;
FIG. 7 is a block diagram of the storage tank dome displacement data restoration device based on deep learning according to a preferred embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
As shown in FIG. 1, a preferred embodiment of the storage tank dome displacement data restoration method based on deep learning of the invention comprises the following steps:
step S1, taking the measuring points with the missing LNG storage tank dome displacement data as measuring points to be repaired, selecting a plurality of measuring points around the measuring points to be repaired as associated measuring points, and acquiring historical displacement data of the measuring points to be repaired in a certain time period before the data missing time period and historical displacement data of the associated measuring points in a corresponding time period. As shown in fig. 2, assuming that the displacement data from time step T to time step (T +1) is missing from the point to be repaired, the displacement data of the point to be repaired K time steps before time step T and the displacement data of the associated point from time step (T-K) to time step (T +1) are obtained.
Then, the historical displacement data of the above-mentioned measuring points are respectively decomposed into a plurality of IMF (Intrinsic Mode Functions) components by an EEMD (ensemble empirical Mode Decomposition) algorithm. The IMF component satisfies the following two conditions:
(1) in the whole time range of the function, the number of the extreme points is equal to or different from the number of the zero crossing points by 1;
(2) at any time point, the mean of the upper envelope and the lower envelope is 0.
As shown in fig. 3, the ensemble empirical mode decomposition algorithm is implemented by the following steps:
step S11, selecting the processing times m of the original signal;
s12, selecting m random white noises with different amplitudes, and combining the original signal with each white noise to obtain m new signals n1(t)，n2(t)，……，nj(t)，……，nm(t); the scales of m white noises are uniformly distributed, and the energy of the white noises is also uniformly distributed on a frequency spectrum.
Step S13, performing EMD (Empirical Mode Decomposition, ensemble Empirical Mode Decomposition) on each of the m new signals to obtain a series of IMF components. In the following, n is defined as1(t) performing EMD as an example to explain the specific process of the EMD algorithm:
step S131, adding n1(t) signal to be decomposed x (t) as EMD.
And S132, screening the signal x (t) to be decomposed. The screening process is to subtract the average envelope function of the signal to be decomposed to obtain a new function; the method specifically comprises the following steps: finding out all maximum value points of the signal x (t) to be decomposed, and fitting an upper envelope line of the signal x (t) to be decomposed by using a cubic spline function; finding out all minimum value points of the signal x (t) to be decomposed, and fitting a cubic spline function into a lower envelope line of the signal x (t) to be decomposed; calculating the mean value of the upper envelope and the lower envelope to obtain a first mean envelope function m1(t); subtracting the first average envelope function m from the signal x (t) to be decomposed1(t) obtaining a first intermediate component function d1,1(t)。
Step S133, determining the intermediate component function d1,1(t) whether two conditions for the IMF component are satisfied, and if so, d1,1(t) is denoted as the first IMF component IMF1(t) of the signal to be decomposed; if not, continue to step S12 for d1,1(t) performing screening until the intermediate component function satisfies the condition of the IMF component. Assuming a medium component function d obtained after K screening1,k(t) if the IMF component is satisfied, d is1,k(t) is noted as the first IMF component of the signal to be decomposed, for n1(t) the first IMF component of which is denoted as a1,1。
Step S134, subtracting the first IMF component from the signal x (t) to be decomposed to obtain a first residual component function r1(t); the first residual component function r1(t) continuing the decomposition (i.e. the separation of the IMF component from the signal by iterative sieving) according to steps S12 and S13 to obtain a second IMF component, for n1(t) the second IMF component of which is denoted as a2,1(ii) a Using a first residual component function r1(t) subtracting the second IMF component to obtain a second residual component function r2(t) of (d). Continuing to apply the second residual component function r according to steps S12 and S132(t) carrying out decomposition; suppose that after N decompositions, the Nth residual component function r is obtainedn(t) is a monotonic function, the decomposition is stopped and the residual component function r is usedn(t) as a residual amount RES. As shown in FIG. 2, at this time, the signal n is applied1(t) is decomposed into n IMF components (i.e., a)1,1、a2,1、……、ai,1、……、aN,1) And a residual amount RES.
According to the above method, n is2(t) decomposition by EMD into i.e. a1,2、a2,2、……、ai,2、……、aN,2；
……；
N is to bej(t) decomposition by EMD into i.e. a1,j、a2,j、……、ai,j、……、aN,j；
……；
N is to bem(t) decomposition by EMD into i.e. a1,m、a2,m、……、ai,m、……、aN,m。
Step S14, respectively averaging IMF components of corresponding modes to obtain a1、a2、……、ai、……、aNAnd obtaining a final IMF component, namely a set empirical mode decomposition result. The formula for averaging is:
compared with Fourier transform and wavelet decomposition, the EMD does not need to set a basis function and has self-adaptability, so that the EMD has a wider application range. After decomposing the signal x (t) to be decomposed, the first IMF component comprises the component with the smallest time scale (the highest frequency) in the signal x (t) to be decomposed, the corresponding frequency component is gradually reduced along with the increase of the order of the IMF component, and r isn(t) (i.e., the residual amount RES in the present embodiment) has the lowest frequency component. According to the convergence condition of EMD decomposition, the residue r obtained by decompositionnWhen (t) is a monotonic function, the time period will be longer than the recording length of the signal, so that the residue r can be reducedn(t) as a trend term for the signal to be decomposed x (t).
Step S2, decomposing the obtained eigenmode function component (namely a)1、a2、……、ai、……、aN) As the input characteristics of the 1DCNN-BilSTM model, extracting the spatial correlation characteristics of the displacement of the associated measuring point and the displacement of the measuring point to be repaired through the 1DCNN (one-dimensional convolutional neural network) model, and then sending the extracted spatial correlation characteristics to a BilSTM (bidirectional long-short memory); bidirectional long-short term memory network) model, and obtaining the dependency characteristics in time. As shown in FIG. 4, the 1DCNN-BilSTM model is formed by splicing the 1DCNN model and the BilSTM model.
CNN is widely used in the field of image processing, and generally, an image is three-dimensional data, that is, X · Y · Z. The time series of the displacement data of one sensor (i.e. measuring point) is 1D, and is decomposed into a plurality of IMF sequences through EEMD, so that the 2D data is changed, and a plurality of sensors are processed at the same time, so that one dimension is added, and finally the data can be regarded as 3D data processing, and the data is processed in a mode similar to image data from the surface. The 1DCNN includes convolutional and pooling layers, and its operating principle is as follows.
The convolutional layer functions to extract the features of a local region, and different convolutional kernels correspond to different feature extractors. The neurons of the convolutional layer are one-dimensional structures as are the fully connected networks. Since the convolutional network is mainly applied to image processing, and an image has a two-dimensional structure, in order to more fully utilize local information of the image, neurons are generally organized into a neural layer having a three-dimensional structure, the size of which is q × width p × depth D, and the neural layer is considered to be formed by D feature maps of a two-dimensional structure of q × p size.
Feature maps (Feature maps) are features extracted by convolution, each of which may be a type of extracted Feature. To improve the representation capability of the convolutional network, multiple different feature maps may be used at each layer to better represent the features.
Without loss of generality, assume the structure of a convolutional layer as follows:
(1) inputting a feature mapping group: x is formed by Rq×p×DIs a three-dimensional Tensor (Tensor); wherein q represents the number of time steps included in the displacement data of one sensor, p represents the number of IMF components obtained by one-time EEMD decomposition of the displacement data of the sensor, and D represents the number of the sensors. Matrix X of each Slice (Slice)d∈Rq×pD is more than or equal to 1 and less than or equal to D.
(2) Outputting a characteristic mapping group: y is formed by the element Rq′×p′×LIs a three-dimensional tensor in which each slice matrix CL ist∈Rq′×p′Is an output characteristic mapping, t is more than or equal to 1 and less than or equal to L; y ═ CL1，CL2，……，CLL]。
(3) And (3) convolution kernel: w is formed as RU×V×D×LIs a four-dimensional tensor(ii) a Where U represents the number of rows of the convolution kernel and V represents the number of columns of the convolution kernel, for example: UxV may take a value of 3 x 5. Each slice matrix Wt,d∈RU×VD is more than or equal to 1 and less than or equal to D; t is more than or equal to 1 and less than or equal to L.
To compute the output feature map Y, a convolution kernel W is usedt,1、Wt,2、……、Wt,DSeparately mapping X to input features1、X2、……、XDConvolution is carried out, then the convolution results are added, and a scalar offset b is added to obtain the net input Z of the convolution layertHere, the Net input means a Net activity value (Net activity) that has not undergone a nonlinear Activation function.
Obtaining output characteristic mapping Y after nonlinear activation functiont。
CLt＝f(Zt)
Wherein
A three-dimensional convolution kernel; btRepresenting a bias matrix; f () is a nonlinear activation function, typically a ReLU function. The calculation process is shown in fig. 5, where the dashed boxes represent convolution kernels. If it is desired to output L feature maps from the convolutional layer, the above calculation process can be repeated L times to obtain L feature maps CL1，CL2，……，CLLL output features SL are obtained after pooling of L feature maps1，SL2，……，SLL. When the input is X ∈ Rq×p×DThe output is Y ∈ Rq′×p′×LEach output signature map requires D filters and one offset in the convolutional layer. Assuming that the size of each filter is U × V, then a total of L × D × (U × V) + L parameters are required.
From the calculation process, the 1DCNN model has the characteristics of local connection, weight sharing and the like, and can reserve and extract the spatial correlation characteristics among IMFs.
The output characteristics of 1DCNN are fed into BilSTM. The BilSTM, i.e., the bidirectional LSTM, is composed of two separate LSTMs (i.e., a forward LSTM and a backward LSTM), and the input features are processed in two ways, one way is from the past to the future and the other way is from the future to the past. The calculation formula is as follows:
wherein x istRepresenting the input characteristics of the BilSTM at the time t, i.e. the output characteristics SL at the corresponding time of 1DCNNt；
Representing a forward propagation hidden state at time t;
representing a forward propagation hidden state at time (t-1);
representing a backward propagation hidden state at time t;
represents a backward propagation hidden state at time (t + 1); o istIndicating time tA hidden layer state; alpha is alphatForward propagating LSTM unit hidden layer output weight for t moment; beta is atThe weight of hidden layer output of the LSTM unit is propagated backwards at the time t; btThe offset corresponding to the hidden layer state at the time t.
As shown in fig. 6, the architecture of the LSTM single neural unit includes an input gate, a forgetting gate, an output gate, and a memory unit, and is used to implement input and output of information, and the operation process is as follows:
Γi＝σ(Wi,xxt+Wi,hht-1+bi)
Γf＝σ(Wf,xxt+Wf,hht-1+bf)
Γo＝σ(Wo,xxt+Wo,hht-1+bo)
ht＝Γo*tanh(Ct)
wherein, Wi,x、Wi,h、Wf,x、Wf,h、Wo,x、Wo,h、Wc,x、Wc,hRepresenting a weight matrix; bi、bf、bc、boRepresenting a bias matrix; x is the number oftRepresenting the input characteristics at time t, i.e. the output characteristics SL at the time corresponding to 1DCNNt；ct-1Representing neurons before updating; c. CtRepresenting the updated neuron; h ist-1The output characteristic of the last moment (t-1 moment in forward transmission and t +1 moment in backward transmission) is represented; h istAn output characteristic representing the current time (i.e., time t); gamma-shapediRepresenting an input gate; gamma-shapedfIndicating a forgetting gate; gamma-shapedoAn output gate is shown;
is a candidate neuron; sigma is a Sigmoid function; tan h is the hyperbolic tangent function.
And step S3, defining a loss function of the 1DCNN-BilSTM model, and ending the training when the value of the loss function of the 1DCNN-BilSTM model converges to a fixed value and keeps unchanged to obtain the EEMD-1DCNN-BilSTM model.
Wherein the loss function l (x, y) of the 1DCNN-BilSTM model can be defined as:
where N represents the number of samples, xiRepresenting the actual value (i.e. true value), y, of the ith sampleiRepresenting the predicted value of the ith sample.
And when the value of the loss function converges to a fixed value and keeps unchanged, considering the parameters of the 1DCNN-BilSTM model at the moment as the optimal model parameters, and stopping the model training.
Step S4, obtaining displacement data of the measuring point to be repaired before the data missing period, and the displacement data of the associated measuring point before the data missing period and the data missing period, inputting the displacement data into an EEMD-1DCNN-BilSTM model to predict the displacement data of the measuring point to be repaired at the data missing period; and taking the predicted displacement data as displacement data of the measuring point to be repaired in the data missing period to finish the repair of the missing data.
The invention also provides a storage tank dome displacement data restoration device based on deep learning, as shown in fig. 7, a preferred embodiment of the storage tank dome displacement data restoration device based on deep learning comprises a displacement data acquisition module, a calculation analysis module and an output module.
The displacement data acquisition module is used for acquiring displacement data of each measuring point of the dome of the LNG storage tank in real time and transmitting the displacement data to the calculation analysis module;
the calculation analysis module is used for monitoring whether displacement data of each measuring point of a dome of the LNG storage tank are missing or not in real time, when the situation that the displacement data of one measuring point is missing is monitored, the measuring point with the missing displacement data is used as a measuring point to be repaired, a plurality of measuring points are selected around the measuring point to be repaired to be used as associated measuring points, the displacement data of the measuring point to be repaired and the displacement data of the associated measuring points are input into an EEMD-1DCNN-BilSTM model, the missing displacement data are predicted, the missing displacement data are supplemented through the predicted displacement data, and data repair is completed.
The calculation analysis module comprises a data reading unit, a monitoring unit, an EEMD-1DCNN-BilSTM model and a storage unit.
The data reading unit is used for reading displacement data of each measuring point of the LNG storage tank dome, which is acquired by the displacement data acquisition module; preferably, a module comprising a GPS data acquisition unit and/or a Beidou positioning data acquisition unit is adopted.
The monitoring unit is used for monitoring whether displacement data of each measuring point of the dome of the LNG storage tank is lost or not in real time;
the EEMD-1DCNN-BilSTM model comprises a set empirical mode decomposition unit and a 1DCNN-BilSTM model, wherein the set empirical mode decomposition unit is used for decomposing displacement data of the measuring points to be repaired and each associated measuring point into a plurality of intrinsic mode function components through a set empirical mode decomposition algorithm, and vectors formed by the intrinsic mode function components are used as input characteristics of the 1DCNN-BilSTM model; the 1DCNN-BilSTM model is used for predicting displacement data of the missing measuring point to be repaired according to input characteristics.
The storage unit is used for storing displacement data of each measuring point of the LNG storage tank dome acquired by the displacement data acquisition module and displacement data predicted by the EEMD-1DCNN-BilSTM model.
The output module is used for outputting the displacement data of each measuring point acquired by the displacement data acquisition module and the repaired displacement data of the measuring point to be repaired. The predictive data output module preferably employs a visualization module, such as a display, to visually output the historical data and the predictive data.
In order to detect whether the prediction deviation of the model is overlarge, the model further comprises a detection unit and an alarm unit, wherein the detection unit is used for appointing a measuring point with normal displacement data as a measuring point to be repaired, predicting the displacement data of the measuring point through the EEMD-1DCNN-BilSTM model, comparing the predicted displacement data with the real displacement data of the measuring point acquired by the displacement data acquisition module, and when the difference value between the predicted displacement data and the real displacement data exceeds a preset threshold value, enabling the alarm unit to output an alarm signal to prompt that the predicted data is overlarge in deviation; thereby alerting the operator that the model may need to be retrained to improve the prediction accuracy of the model. Of course, the operator does not handle the alarm and does not affect the model operation.
In this embodiment, the analysis module adopts the EEMD algorithm and the 1DCNN-BiLSTM model, and has low requirements on calculation and storage capabilities, low requirements on hardware, and low implementation cost.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (10)
1. A storage tank dome displacement data restoration method based on deep learning is used for restoration when LNG storage tank dome displacement data are missing, and is characterized by comprising the following steps:
step S1, taking a measuring point with LNG storage tank dome displacement data missing as a measuring point to be repaired, selecting a plurality of measuring points around the measuring point to be repaired as associated measuring points, acquiring historical displacement data of the measuring point to be repaired in a certain period before the data missing period and historical displacement data of the associated measuring points in a corresponding period, and decomposing the historical displacement data of the measuring points into a plurality of intrinsic mode function components respectively through a set empirical mode decomposition algorithm;
step S2, taking the intrinsic mode function component obtained through decomposition as an input feature of a 1DCNN-BilSTM model, extracting a spatial correlation feature of the displacement of the associated measuring point and the displacement of the measuring point to be repaired through the 1DCNN model, and then sending the extracted spatial correlation feature into the BilSTM model to obtain a dependency characteristic in time;
step S3, defining a loss function of the 1DCNN-BilSTM model, and ending training when the value of the loss function of the 1DCNN-BilSTM model converges to a fixed value and keeps unchanged to obtain an EEMD-1DCNN-BilSTM model;
step S4, obtaining displacement data of the measuring point to be repaired before the data missing period and displacement data of the associated measuring point before the data missing period and the data missing period, inputting the displacement data into an EEMD-1DCNN-BilSTM model to predict the displacement data of the measuring point to be repaired at the data missing period; and taking the predicted displacement data as displacement data of the measuring point to be repaired in the data missing period to finish the repair of the missing data.
2. The deep learning-based storage tank dome displacement data restoration method according to claim 1, wherein the ensemble empirical mode decomposition algorithm is implemented by the following steps:
step S11, selecting the processing times m of the original signal;
s12, selecting m random white noises with different amplitudes, and combining the original signal with each white noise respectively to obtain m new signals;
step S13, performing empirical mode decomposition on the m new signals respectively to obtain a series of intrinsic mode function components;
and step S14, respectively averaging the intrinsic mode function components of the corresponding modes to obtain a set empirical mode decomposition result.
3. The method for repairing displacement data of the storage tank dome based on the deep learning as claimed in claim 2, wherein m scales of the white noise are uniformly distributed, and the energy of the white noise is also uniformly distributed in a frequency spectrum.
4. The deep learning-based storage tank dome displacement data restoration method according to claim 2, wherein the empirical mode decomposition algorithm is implemented by the following steps:
s131, taking a new signal obtained by combining the original signal and white noise as a signal x (t) to be decomposed, wherein t represents time;
s132, screening a signal x (t) to be decomposed; the method specifically comprises the following steps: finding out all maximum value points of the signal x (t) to be decomposed, and fitting the maximum value points into an upper envelope curve of the signal to be decomposed; finding out all minimum value points of the signal x (t) to be decomposed, and fitting the minimum value points into a lower envelope curve of the signal to be decomposed; calculating the mean value of the upper envelope and the lower envelope to obtain the mean envelope m of the signal x (t) to be decomposed1(t); subtracting m from the signal x (t) to be decomposed1(t) obtaining an intermediate component function d1,1(t)；
Step S133, judgment d1,1(t) whether the condition for the eigenmode function component is satisfied, and if not, d1,1(t) instead of the signal to be decomposed x (t), d continues in step S121,1(t) screening, and marking the signal after K times of screening as d1,k(t) up to d1,k(t) when the condition of the eigenmode function component is satisfied, the first IMF component IMF1(t) of the signal x (t) to be decomposed is marked;
step S134, subtracting the first IMF component IMF1(t) from the signal x (t) to be decomposed to obtain a residual component r1(t) to r1(t) continuing the decomposition in steps S12 and S13; after n decompositions, the residual signal r is obtainedn(t); when r isn(t) when the function is a monotonic function, the decomposition is stopped and the residual component function r is usedn(t) as a residual amount RES.
5. The method for restoring displacement data of the storage tank dome based on deep learning as claimed in claim 4, wherein the eigenmode function component satisfies the following condition:
in the whole time range of the function, the number of the extreme points is equal to or different from the number of the zero crossing points by 1;
at any time point, the mean of the upper envelope and the lower envelope is 0.
6. The deep learning-based storage tank dome displacement data restoration method according to claim 1, wherein the time series of displacement data of one measuring point forms one-dimensional data; decomposing the one-dimensional data into a plurality of IMF sequences through EEMD to form two-dimensional data; and after data of a plurality of associated measuring points are obtained, three-dimensional data are formed and are used as an input feature mapping group of the 1DCNN model.
7. The method for restoring displacement data of a storage tank dome based on deep learning as claimed in claim 1, wherein the loss function l (x, y) of the 1DCNN-BilSTM model is defined as:
where N represents the number of samples, xiDenotes the actual value of the i-th sample, yiRepresenting the predicted value of the ith sample.
8. A storage tank dome displacement data prosthetic devices based on deep learning, characterized in that includes:
the displacement data acquisition module is used for acquiring displacement data of each measuring point of the dome of the LNG storage tank in real time and transmitting the displacement data to the calculation analysis module;
the calculation analysis module is used for monitoring whether displacement data of each measuring point of a dome of the LNG storage tank are missing or not in real time, when the displacement data of one measuring point is monitored to be missing, the measuring point with the missing displacement data is used as a measuring point to be repaired, a plurality of measuring points are selected around the measuring point to be repaired to be used as associated measuring points, the displacement data of the measuring point to be repaired and the displacement data of the associated measuring points are input into an EEMD-1DCNN-BilSTM model, the missing displacement data are predicted, the missing displacement data are supplemented by the predicted displacement data, and data repair is completed; and
and the output module is used for outputting the displacement data of each measuring point acquired by the displacement data acquisition module and the repaired displacement data of the measuring point to be repaired.
9. The deep learning-based storage tank dome displacement data restoration device according to claim 8, wherein the calculation analysis module comprises a data reading unit, a monitoring unit, an EEMD-1DCNN-BilSTM model and a storage unit;
the data reading unit is used for reading displacement data of each measuring point of the LNG storage tank dome, which is acquired by the displacement data acquisition module;
the monitoring unit is used for monitoring whether displacement data of each measuring point of the dome of the LNG storage tank is lost or not in real time;
the EEMD-1DCNN-BilSTM model comprises a set empirical mode decomposition unit and a 1DCNN-BilSTM model, wherein the set empirical mode decomposition unit is used for decomposing displacement data of the measuring points to be repaired and each associated measuring point into a plurality of intrinsic mode function components through a set empirical mode decomposition algorithm, and vectors formed by the intrinsic mode function components are used as input characteristics of the 1DCNN-BilSTM model; the 1DCNN-BilSTM model is used for predicting displacement data of missing measuring points to be repaired according to input characteristics;
the storage unit is used for storing displacement data of each measuring point of the LNG storage tank dome acquired by the displacement data acquisition module and displacement data predicted by the EEMD-1DCNN-BilSTM model.
10. The storage tank dome displacement data restoration device based on deep learning as claimed in claim 8, further comprising a detection unit and an alarm unit, wherein the detection unit is used for designating a measurement point with normal displacement data as a measurement point to be restored, comparing the displacement data of the measurement point predicted by the EEMD-1DCNN-BilSTM model with the real displacement data of the measurement point collected by the displacement data collection module, and when the difference between the displacement data and the measurement point exceeds a preset threshold, enabling the alarm unit to output an alarm signal to prompt that the predicted data is over-shifted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111030325.0A CN113688773B (en) | 2021-09-03 | 2021-09-03 | Storage tank dome displacement data restoration method and device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111030325.0A CN113688773B (en) | 2021-09-03 | 2021-09-03 | Storage tank dome displacement data restoration method and device based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113688773A true CN113688773A (en) | 2021-11-23 |
| CN113688773B CN113688773B (en) | 2023-09-26 |
Family
ID=78585144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111030325.0A Active CN113688773B (en) | 2021-09-03 | 2021-09-03 | Storage tank dome displacement data restoration method and device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688773B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117687044A (en) * | 2023-11-02 | 2024-03-12 | 昆明理工大学 | Deep learning method for satellite-borne GNSS-R global sea surface effective wave height estimation |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0756746A1 (en) * | 1995-02-16 | 1997-02-05 | Gemplus | Method for the secure updating of an eeprom memory |
| CN103206614A (en) * | 2013-04-01 | 2013-07-17 | 中山大学 | Early-warning device and early-warning method used for monitoring accidents of boiling liquid expanding vapor explosion (BLEVE) of pressuring-bearing storage tanks |
| US20160072891A1 (en) * | 2014-09-08 | 2016-03-10 | Leeo, Inc. | Sensor-data sub-contracting during environmental monitoring |
| CN105760839A (en) * | 2016-02-22 | 2016-07-13 | 重庆大学 | Bearing fault diagnosis method based on multi-feature manifold learning and support vector machine |
| CN109615014A (en) * | 2018-12-17 | 2019-04-12 | 清华大学 | A kind of data sorting system and method based on the optimization of KL divergence |
| CN110333076A (en) * | 2019-06-19 | 2019-10-15 | 电子科技大学 | Method for Bearing Fault Diagnosis based on CNN-Stacking |
| US20190339684A1 (en) * | 2016-05-09 | 2019-11-07 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection, learning, and streaming of machine signals for analytics and maintenance using the industrial internet of things |
| CN110909931A (en) * | 2019-11-20 | 2020-03-24 | 成都理工大学 | Logging curve prediction method based on modal decomposition reconstruction and depth LSTM-RNN model |
| CN111240268A (en) * | 2020-01-14 | 2020-06-05 | 重庆大学 | Axle system thermal error modeling method and thermal error compensation system based on SLSTM neural network |
| CN112478483A (en) * | 2020-12-01 | 2021-03-12 | 华设设计集团股份有限公司 | Automatic monitoring and early warning method and system for hazardous chemical substance normal-pressure storage tank |
-
2021
- 2021-09-03 CN CN202111030325.0A patent/CN113688773B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0756746A1 (en) * | 1995-02-16 | 1997-02-05 | Gemplus | Method for the secure updating of an eeprom memory |
| CN103206614A (en) * | 2013-04-01 | 2013-07-17 | 中山大学 | Early-warning device and early-warning method used for monitoring accidents of boiling liquid expanding vapor explosion (BLEVE) of pressuring-bearing storage tanks |
| US20160072891A1 (en) * | 2014-09-08 | 2016-03-10 | Leeo, Inc. | Sensor-data sub-contracting during environmental monitoring |
| CN105760839A (en) * | 2016-02-22 | 2016-07-13 | 重庆大学 | Bearing fault diagnosis method based on multi-feature manifold learning and support vector machine |
| US20190339684A1 (en) * | 2016-05-09 | 2019-11-07 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection, learning, and streaming of machine signals for analytics and maintenance using the industrial internet of things |
| CN109615014A (en) * | 2018-12-17 | 2019-04-12 | 清华大学 | A kind of data sorting system and method based on the optimization of KL divergence |
| CN110333076A (en) * | 2019-06-19 | 2019-10-15 | 电子科技大学 | Method for Bearing Fault Diagnosis based on CNN-Stacking |
| CN110909931A (en) * | 2019-11-20 | 2020-03-24 | 成都理工大学 | Logging curve prediction method based on modal decomposition reconstruction and depth LSTM-RNN model |
| CN111240268A (en) * | 2020-01-14 | 2020-06-05 | 重庆大学 | Axle system thermal error modeling method and thermal error compensation system based on SLSTM neural network |
| CN112478483A (en) * | 2020-12-01 | 2021-03-12 | 华设设计集团股份有限公司 | Automatic monitoring and early warning method and system for hazardous chemical substance normal-pressure storage tank |
Non-Patent Citations (1)
| Title |
|---|
| ZENGSHUN CHEN等: ""An improved method based on EEMD-LSTM to predict missing measured data of structural sensors"", 《APPLIED SCIENCES》, vol. 12, no. 8, pages 1 - 26 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117687044A (en) * | 2023-11-02 | 2024-03-12 | 昆明理工大学 | Deep learning method for satellite-borne GNSS-R global sea surface effective wave height estimation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113688773B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Postels et al. | Sampling-free epistemic uncertainty estimation using approximated variance propagation | |
| CN109947086B (en) | Mechanical fault migration diagnosis method and system based on counterstudy | |
| CN111832216B (en) | Rolling bearing residual service life prediction method based on EEMD-MCNN-GRU | |
| Baraldi et al. | Differential evolution-based multi-objective optimization for the definition of a health indicator for fault diagnostics and prognostics | |
| CN110361778B (en) | Seismic data reconstruction method based on generation countermeasure network | |
| EP2327019B1 (en) | Systems and methods for real time classification and performance monitoring of batch processes | |
| CN111767930A (en) | Method for detecting abnormal time series data of Internet of things and related equipment thereof | |
| Aydemir et al. | Image-based prognostics using deep learning approach | |
| CN117540174B (en) | Building structure multi-source heterogeneous data intelligent analysis system and method based on neural network | |
| Dezert et al. | Edge detection in color images based on DSmT | |
| CN113988357A (en) | High-rise building wind-induced response prediction method and device based on deep learning | |
| DE112018004348T5 (en) | METHODS, DEVICES AND SYSTEMS FOR MONITORING DEVICES | |
| CN113688773A (en) | Storage tank dome displacement data restoration method and device based on deep learning | |
| JP7225731B2 (en) | Imaging multivariable data sequences | |
| CN113743297A (en) | Storage tank dome displacement data restoration method and device based on deep learning | |
| CN113688770A (en) | Long-term wind pressure missing data completion method and device for high-rise building | |
| Warner et al. | A computationally-efficient probabilistic approach to model-based damage diagnosis | |
| Favorskaya et al. | Image inpainting based on self-organizing maps by using multi-agent implementation | |
| CN115984606A (en) | Planetary gear fault diagnosis method and system based on CEEMDAN denoising | |
| CN115130519A (en) | Ship structure fault prediction method using convolutional neural network | |
| CN115131832A (en) | Priori learning restoration-based ultrasonic guided wave inversion method suitable for fingerprint identification | |
| CN116934603A (en) | Logging curve missing segment completion method and device, storage medium and electronic equipment | |
| CN114298101A (en) | Dynamic weighing method and system | |
| Colace et al. | Unsupervised Learning Techniques for Vibration-Based Structural Health Monitoring Systems Driven by Data: A General Overview | |
| CN113762203B (en) | Cross-domain self-adaptive SAR image classification method, device and equipment based on simulation data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |